Northeastern University is a global research university recognized for its cooperative education model and leadership in network science, cybersecurity, and AI. It integrates experiential learning with interdisciplinary research. NEC Labs America and Northeastern University work together on scalable graph learning, misinformation detection, and secure federated graph analytics. Please read about our latest news and collaborative publications with Northeastern University.
Learn about the amazing group of interns who joined us at Princeton and San Jose campuses this summer. Their hard work, fresh perspectives, and dedication have truly made an impact across the board, from cutting-edge research projects to innovative software development initiatives.
We propose a vision-LLM framework for automating development and deployment of computer vision solutions for pre-defined or custom-defined tasks. A foundational layer is proposed with a code-LLM AI orchestrator self-trained with reinforcement learning to create Python code based on its understanding of a novel user-defined task, together with APIs, documentation and usage notes of existing task-specific AI models. Zero-shot abilities in specific domains are obtained through foundational vision-language models trained at a low compute expense leveraging existing computer vision models and datasets. An engine layer is proposed which comprises of several task-specific vision-language engines which can be compositionally utilized. An application-specific layer is proposed to improve performance in customer-specific scenarios, using novel LLM-guided data augmentation and question decomposition, besides standard fine-tuning tools. We demonstrate a range of applications including visual AI assistance, visual conversation, law enforcement, mobility, medical image reasoning and remote sensing.
Visual program synthesis is a promising approach to exploit the reasoning abilities of large language models for compositional computer vision tasks. Previous work has used few-shot prompting with frozen LLMs to synthesize visual programs. Training an LLM to write better visual programs is an attractive prospect, but it is unclear how to accomplish this. No dataset of visual programs for training exists, and acquisition of a visual program dataset cannot be easily crowdsourced due to the need for expert annotators. To get around the lack of direct supervision, we explore improving the program synthesis abilities of an LLM using feedback from interactive experience. We propose a method where we exploit existing annotations for a vision-language task to improvise a coarse reward signal for that task, treat the LLM as a policy, and apply reinforced self-training to improve the visual program synthesis ability of the LLM for that task. We describe a series of experiments on object detection, compositional visual question answering, and image-text retrieval, and show that in each case, the self-trained LLM outperforms or performs on par with few-shot frozen LLMs that are an order of magnitude larger. Website: https://zaidkhan.me/ViReP/
Visual question answering (VQA) has traditionally been treated as a single-step task where each question receives the same amount of effort, unlike natural human question-answering strategies. We explore a question decomposition strategy for VQA to overcome this limitation. We probe the ability of recently developed large vision-language models to use human-written decompositions and produce their own decompositions of visual questions, finding they are capable of learning both tasks from demonstrations alone. However, we show that naive application of model-written decompositions can hurt performance. We introduce a model-driven selective decomposition approach for second-guessing predictions and correcting errors, and validate its effectiveness on eight VQA tasks across three domains, showing consistent improvements in accuracy, including improvements of >20% on medical VQA datasets and boosting the zero-shot performance of BLIP-2 above chance on a VQA reformulation of the challenging Winoground task. Project Site: https://zaidkhan.me/decomposition-0shot-vqa/
Cross-Domain Detection (XDD) aims to train a domain-adaptive object detector using unlabeled images from a target domain and labeled images from a source domain. Existing approaches achieve this either by aligning the feature maps or the region proposals from the two domains, or by transferring the style of source images to that of target images. In this paper, rather than proposing another method following the existing lines, we introduce a new framework complementary to existing methods. Our framework unifies some popular Self-Supervised Learning (SSL) techniques (e.g., rotation angle prediction, strong/weak data augmentation, mean teacher modeling) and adapts them to the XDD task. Our basic idea is to leverage the unsupervised nature of these SSL techniques and apply them simultaneously across domains (source and target) and models (student and teacher). These SSL techniques can thus serve as shared bridges that facilitate knowledge transfer between domains. More importantly, as these techniques are independently applied in each domain, they are complementary to existing domain alignment techniques that relies on interactions between domains (e.g., adversarial alignment). We perform extensive analyses on these SSL techniques and show that they significantly improve the performance of existing methods. In addition, we reach comparable or even better performance than the state-of-the-art methods when integrating our framework with an old well-established method.
Finetuning a large vision language model (VLM) on a target dataset after large scale pretraining is a dominant paradigm in visual question answering (VQA). Datasets for specialized tasks such as knowledge-based VQA or VQA in non natural-image domains are orders of magnitude smaller than those for general-purpose VQA. While collecting additional labels for specialized tasks or domains can be challenging, unlabeled images are often available. We introduce SelTDA (Self-Taught Data Augmentation), a strategy for finetuning large VLMs on small-scale VQA datasets. SelTDA uses the VLM and target dataset to build a teacher model that can generate question-answer pseudolabels directly conditioned on an image alone, allowing us to pseudolabel unlabeled images. SelTDA then finetunes the initial VLM on the original dataset augmented with freshly pseudolabeled images. We describe a series of experiments showing that our self-taught data augmentation increases robustness to adversarially searched questions, counterfactual examples, and rephrasings, it improves domain generalization, and results in greater retention of numerical reasoning skills. The proposed strategy requires no additional annotations or architectural modifications, and is compatible with any modern encoder-decoder multimodal transformer. Code available at https://github.com/codezakh/SelTDA
Self-supervised vision-language pretraining from pure images and text with a contrastive loss is effective, but ignores fine-grained alignment due to a dual-stream architecture that aligns image and text representations only on a global level. Earlier, supervised, non-contrastive methods were capable of finer-grained alignment, but required dense annotations that were not scalable. We propose a single stream architecture that aligns images and language at multiple levels: global, fine-grained patch-token, and conceptual/semantic, using two novel tasks: symmetric cross-modality reconstruction (XMM) and a pseudo-labeled key word prediction (PSL). In XMM, we mask input tokens from one modality and use cross-modal information to reconstruct the masked token, thus improving fine-grained alignment between the two modalities. In PSL, we use attention to select keywords in a caption, use a momentum encoder to recommend other important keywords that are missing from the caption but represented in the image, and then train the visual encoder to predict the presence of those keywords, helping it learn semantic concepts that are essential for grounding a textual token to an image region. We demonstrate competitive performance and improved data efficiency on image-text retrieval, grounding, visual question answering/reasoning against larger models and models trained on more data. Code and models available at zaidkhan.me/SIMLA.
Convolutional Neural Networks have achieved remarkable success in face recognition, in part due to the abundant availability of data. However, the data used for training CNNs is often imbalanced. Prior works largely focus on the long-tailed nature of face datasets in data volume per identity or focus on single bias variation. In this paper, we show that many bias variations such as ethnicity, head pose, occlusion and blur can jointly affect the accuracy significantly. We propose a sample level weighting approach termed Multi-variation Cosine Margin (MvCoM), to simultaneously consider the multiple variation factors, which orthogonally enhances the face recognition losses to incorporate the importance of training samples. Further, we leverage a learning to learn approach, guided by a held-out meta learning set and use an additive modeling to predict the MvCoM. Extensive experiments on challenging face recognition benchmarks demonstrate the advantages of our method in jointly handling imbalances due to multiple variations.
Retailers are aiming to enhance customer experience by automating the checkout process. The key impediment here is the effort to manually align the product barcode with the scanner, requiring sequential handling of items without blocking the line-of-sight of the laser beam. While recent systems such as Amazon Go eliminate human involvement using an extensive array of cameras, we propose a privacy-preserving alternative, RFGo, that identifies products using passive RFID tags. Foregoing continuous monitoring of customers throughout the store, RFGo scans the products in a dedicated checkout area that is large enough for customers to simply walk in and stand until the scan is complete (in two seconds). Achieving such low-latency checkout is not possible with traditional RFID readers, which decode tags using one antenna at a time. To overcome this, RFGo includes a custom-built RFID reader that simultaneously decodes a tag’s response from multiple carrier-level synchronized antennas enabling a large set of tag observations in a very short time. RFGo then feeds these observations to a neural network that accurately distinguishes the products within the checkout area from those that are outside. We build a prototype of RFGo and evaluate its performance in challenging scenarios. Our experiments show that RFGo is extremely accurate, fast and well-suited for practical deployment in apparel stores.
Inductive and unsupervised graph learning is a critical technique for predictive or information retrieval tasks where label information is difficult to obtain. It is also challenging to make graph learning inductive and unsupervised at the same time, as learning processes guided by reconstruction error based loss functions inevitably demand graph similarity evaluation that is usually computationally intractable. In this paper, we propose a general framework SEED (Sampling, Encoding, and Embedding Distributions) for inductive and unsupervised representation learning on graph structured objects. Instead of directly dealing with the computational challenges raised by graph similarity evaluation, given an input graph, the SEED framework samples a number of subgraphs whose reconstruction errors could be efficiently evaluated, encodes the subgraph samples into a collection of subgraph vectors, and employs the embedding of the subgraph vector distribution as the output vector representation for the input graph. By theoretical analysis, we demonstrate the close connection between SEED and graph isomorphism. Using public benchmark datasets, our empirical study suggests the proposed SEED framework is able to achieve up to 10% improvement, compared with competitive baseline methods.