Rutgers University (Rutgers, The State University of New Jersey) is New Jersey’s flagship public university, with top research in medicine, AI, and environmental science. It bridges academic excellence with public service and global research impact. NEC Labs America partners with Rutgers University on edge AI, secure speech modeling, and privacy-preserving acoustic analytics. Please read about our latest news and collaborative publications with Rutgers University.

Posts

Improving Language-Based Object Detection by Explicit Generation of Negative Examples

/in /by

The recent progress in language-based object detection with an open-vocabulary can be largely attributed to finding better ways of leveraging large-scale data with free-form text annotations. Training from image captions with grounded bounding boxes (ground truth or pseudo-labeled) enable the models to reason over an open-vocabulary and understand object descriptions in free-form text. In this work, we investigate the role of negative captions for training such language-based object detectors. While the fixed label space in standard object detection datasets clearly defines the set of negative classes, the free-form text used for language-based detection makes the space of potential negatives virtually infinite in size. We propose to leverage external knowledge bases and large-language-models to automatically generate contradictions for each caption in the training dataset. Furthermore, we leverage image-generate tools to create corresponding negative images to the contradicting caption. Such automatically generated data constitute hard negative examples for language-based detection and improve the model when trained from. Our experiments demonstrate the benefits of the automatically generated training data on two complex benchmarks.

Read more

MSI: Maximize Support-Set Information for Few-Shot Segmentation

/in /by

Few-Shot Segmentation FSS (Few-shot segmentation) aims to segment a target class using a small number of labeled images (support set). To extract information relevant to the target class, a dominant approach in best performing FSS methods removes background features using a support mask. We observe that this feature excision through a limiting support mask introduces an information bottleneck in several challenging FSS cases, e.g., for small targets and/or inaccurate target boundaries. To this end, we present a novel method (MSI), which maximizes the support-set information by exploiting two complementary sources of features to generate super correlation maps. We validate the effectiveness of our approach by instantiating it into three recent and strong FSS methods. Experimental results on several publicly available FSS benchmarks show that our proposed method consistently improves performance by visible margins and leads to faster convergence.

Read more

OmniLabel: A Challenging Benchmark for Language-Based Object Detection

/in /by

Language-based object detection is a promising direction towards building a natural interface to describe objects in images that goes far beyond plain category names. While recent methods show great progress in that direction, proper evaluation is lacking. With OmniLabel, we propose a novel task definition, dataset, and evaluation metric. The task subsumes standard and open-vocabulary detection as well as referring expressions. With more than 30K unique object descriptions on over 25K images, OmniLabel provides a challenge benchmark with diverse and complex object descriptions in a naturally open-vocabulary setting. Moreover, a key differentiation to existing benchmarks is that our object descriptions can refer to one, multiple or even no object, hence, providing negative examples in free-form text. The proposed evaluation handles the large label space and judges performance via a modified average precision metric, which we validate by evaluating strong language-based baselines. OmniLabel indeed provides a challenging test bed for future research on language-based detection.

Read more

Improving Pseudo Labels for Open-Vocabulary Object Detection

/in /by

Recent studies show promising performance in open-vocabulary object detection (OVD) using pseudo labels (PLs) from pretrained vision and language models (VLMs). However, PLs generated by VLMs are extremely noisy due to the gap between the pretraining objective of VLMs and OVD, which blocks further advances on PLs. In this paper, we aim to reduce the noise in PLs and propose a method called online Self-training And a Split-and-fusion head for OVD (SAS-Det). First, the self-training finetunes VLMs to generate high quality PLs while prevents forgetting the knowledge learned in the pretraining. Second, a split-and-fusion (SAF) head is designed to remove the noise in localization of PLs, which is usually ignored in existing methods. It also fuses complementary knowledge learned from both precise ground truth and noisy pseudo labels to boost the performance. Extensive experiments demonstrate SAS-Det is both efficient and effective. Our pseudo labeling is 3 times faster than prior methods. SAS-Det outperforms prior state-of-the-art models of the same scale by a clear margin and achieves 37.4 AP50 and 27.3 APr on novel categories of the COCO and LVIS benchmarks, respectively.

Read more

Beyond One Model Fits All: A Survey of Domain Specialization for Large Language Models

/in /by

Large language models (LLMs) have significantly advanced the field of natural language processing (NLP), providing a highly useful, task agnostic foundation for a wide range of applications. The great promise of LLMs as general task solvers motivated people to extend their functionality largely beyond just a “chatbot”, and use it as an assistant or even replacement for domain experts and tools in specific domains such as healthcare, finance, and education. However, directly applying LLMs to solve sophisticated problems in specific domains meets many hurdles, caused by the heterogeneity of domain data, the sophistication of domain knowledge, the uniqueness of domain objectives, and the diversity of the constraints (e.g., various social norms, cultural conformity, religious beliefs, and ethical standards in the domain applications). To fill such a gap, explosively increase research, and practices have been conducted in very recent years on the domain specialization of LLMs, which, however, calls for a comprehensive and systematic review to better summarizes and guide this promising domain. In this survey paper, first, we propose a systematic taxonomy that categorizes the LLM domain specialization techniques based on the accessibility to LLMs and summarizes the framework for all the subcategories as well as their relations and differences to each other. We also present a comprehensive taxonomy of critical application domains that can benefit from specialized LLMs, discussing their practical significance and open challenges. Furthermore, we offer insights into the current research status and future trends in this area.

Read more

Semi-supervised Identification and Mapping of Water Accumulation Extent using Street-level Monitoring Videos

/in /by

Urban flooding is becoming a common and devastating hazard, which causes life loss and economic damage. Monitoring and understanding urban flooding in a highly localized scale is a challenging task due to the complicated urban landscape, intricate hydraulic process, and the lack of high-quality and resolution data. The emerging smart city technology such as monitoring cameras provides an unprecedented opportunity to address the data issue. However, estimating water ponding extents on land surfaces based on monitoring footage is unreliable using the traditional segmentation technique because the boundary of the water ponding, under the influence of varying weather, background, and illumination, is usually too fuzzy to identify, and the oblique angle and image distortion in the video monitoring data prevents georeferencing and object-based measurements. This paper presents a novel semi-supervised segmentation scheme for surface water extent recognition from the footage of an oblique monitoring camera. The semi-supervised segmentation algorithm was found suitable to determine the water boundary and the monoplotting method was successfully applied to georeference the pixels of the monitoring video for the virtual quantification of the local drainage process. The correlation and mechanism-based analysis demonstrate the value of the proposed method in advancing the understanding of local drainage hydraulics. The workflow and created methods in this study have a great potential to study other street level and earth surface processes.

Read more

Exploiting Unlabeled Data with Vision and Language Models for Object Detection

/in /by

Building robust and generic object detection frameworks requires scaling to larger label spaces and bigger training datasets. However, it is prohibitively costly to acquire annotations for thousands of categories at a large scale. We propose a novel method that leverages the rich semantics available in recent vision and language models to localize and classify objects in unlabeled images, effectively generating pseudo labels for object detection. Starting with a generic and class-agnostic region proposal mechanism, we use vision and language models to categorize each region of an image into any object category that is required for downstream tasks. We demonstrate the value of the generated pseudo labels in two specific tasks, open-vocabulary detection, where a model needs to generalize to unseen object categories, and semi-supervised object detection, where additional unlabeled images can be used to improve the model. Our empirical evaluation shows the effectiveness of the pseudo labels in both tasks, where we outperform competitive baselines and achieve a novel state-of-the-art for open-vocabulary object detection. Our code is available at https://github.com/xiaofeng94/VL-PLM.

Read more

COMPOSER: Compositional Reasoning of Group Activity in Videos with Keypoint-Only Modality

/in /by

Group Activity Recognition detects the activity collectively performed by a group of actors, which requires compositional reasoning of actors and objects. We approach the task by modeling the video as tokens that represent the multi-scale semantic concepts in the video. We propose COMPOSER, a Multiscale Transformer based architecture that performs attention-based reasoning over tokens at each scale and learns group activity compositionally. In addition, prior works suffer from scene biases with privacy and ethical concerns. We only use the keypoint modality which reduces scene biases and prevents acquiring detailed visual data that may contain private or biased information of users. We improve the multiscale representations in COMPOSER by clustering the intermediate scale representations, while maintaining consistent cluster assignments between scales. Finally, we use techniques such as auxiliary prediction and data augmentations tailored to the keypoint signals to aid model training. We demonstrate the model’s strength and interpretability on two widely-used datasets (Volleyball and Collective Activity). COMPOSER achieves up to +5.4% improvement with just the keypoint modality (Code is available at https://github.com/hongluzhou/composer.).

Read more

Multi-Faceted Knowledge-Driven Pre-training for Product Representation Learning

/in /by

As a key component of e-commerce computing, product representation learning (PRL) provides benefits for a variety of applications, including product matching, search, and categorization. The existing PRL approaches have poor language understanding ability due to their inability to capture contextualized semantics. In addition, the learned representations by existing methods are not easily transferable to new products. Inspired by the recent advance of pre-trained language models (PLMs), we make the attempt to adapt PLMs for PRL to mitigate the above issues. In this article, we develop KINDLE, a Knowledge-drIven pre-trainiNg framework for proDuct representation LEarning, which can preserve the contextual semantics and multi-faceted product knowledge robustly and flexibly. Specifically, we first extend traditional one-stage pre-training to a two-stage pre-training framework and exploit a deliberate knowledge encoder to ensure a smooth knowledge fusion into PLM. In addition, we propose a multi-objective heterogeneous embedding method to represent thousands of knowledge elements. This helps KINDLE calibrate knowledge noise and sparsity automatically by replacing isolated classes as training targets in knowledge acquisition tasks. Furthermore, an input-aware gating network is proposed to select the most relevant knowledge for different downstream tasks. Finally, extensive experiments have demonstrated the advantages of KINDLE over the state-of-the-art baselines across three downstream tasks.

Read more

Towards Learning Disentangled Representations for Time Series

/in /by

Promising progress has been made toward learning efficient time series representations in recent years, but the learned representations often lack interpretability and do not encode semantic meanings by the complex interactions of many latent factors. Learning representations that disentangle these latent factors can bring semantic-rich representations of time series and further enhance interpretability. However, directly adopting the sequential models, such as Long Short-Term Memory Variational AutoEncoder (LSTM-VAE), would encounter a Kullback?Leibler (KL) vanishing problem: the LSTM decoder often generates sequential data without efficiently using latent representations, and the latent spaces sometimes could even be independent of the observation space. And traditional disentanglement methods may intensify the trend of KL vanishing along with the disentanglement process, because they tend to penalize the mutual information between the latent space and the observations. In this paper, we propose Disentangle Time-Series, a novel disentanglement enhancement framework for time series data. Our framework achieves multi-level disentanglement by covering both individual latent factors and group semantic segments. We propose augmenting the original VAE objective by decomposing the evidence lower-bound and extracting evidence linking factorial representations to disentanglement. Additionally, we introduce a mutual information maximization term between the observation space to the latent space to alleviate the KL vanishing problem while preserving the disentanglement property. Experimental results on five real-world IoT datasets demonstrate that the representations learned by DTS achieve superior performance in various tasks with better interpretability.

Read more