Abhishek Aich NEC Labs AmericaAbhishek Aich is a Researcher in the Media Analytics Department at NEC Laboratories America. He received his Bachelor of Technology (B.Tech.) in Electronics and Communications Engineering at Biju Patnaik University of Technology, Odisha, India, Master of Science (M.S.) in Electronics and Communication Engineering at National Institute of Technology, Tiruchirappalli, India and his Ph.D. in 2023 in Electrical and Computer Engineering from the University of California, Riverside, USA. At UC Riverside, he worked with Prof. Amit K. Roy-Chowdhury on topics in computer vision and deep learning.

At NEC Labs, Dr. Aich’s work focuses on vision-language frameworks, perception problems for autonomous driving, dynamic multi-task architectures, efficient transformers, and generative AI. His recent contributions include research on progressive token length scaling for universal segmentation (presented at ICLR 2025, and efficiency–accuracy trade-offs in DETR-style models (CVPRW 2024). He has also helped organize key workshops at ICCV, AAAI, and WACV, and was part of the winning team in the U.S. DOT Intersection Safety Challenge 2025, earning top recognition in Stage 1B.

 

Posts

Image-Specific Adaptation of Transformer Encoders for Compute-Efficient Segmentation

/in /by

Vision transformer-based models bring significant improvements for image segmentation tasks. Although these architectures offer powerful capabilities irrespective of specific segmentation tasks, their use of computational resources can be taxing on deployed devices. One way to overcome this challenge is by adapting the computation level to the specific needs of the input image rather than the current one-size-fits-all approach. To this end, we introduce ECO-M2F or EffiCient TransfOrmer Encoders for Mask2Former-style models. Noting that the encoder module of M2F-style models incurs high resource-intensive computations, ECO-M2F provides a strategy to self-select the number of hidden layers in the encoder, conditioned on the input image. To enable this self-selection ability for providing a balance between performance and computational efficiency, we present a three-step recipe. The first step is to train the parent architecture to enable early exiting from the encoder. The second step is to create a derived dataset of the ideal number of encoder layers required for each training example. The third step is to use the aforementioned derived dataset to train a gating network that predicts the number of encoder layers to be used, conditioned on the input image. Additionally, to change the computational-accuracy tradeoff, only steps two and three need to be repeated, which significantly reduces retraining time. Experiments on the public datasets show that the proposed approach reduces expected encoder computational cost while maintaining performance, adapts to various user compute resources, is flexible in architecture configurations, and can be extended beyond the segmentation task to object detection.

Read more

iFinder: Structured Zero-Shot Vision-Based LLM Grounding for Dash-Cam Video Reasoning

/0 Comments/in /by

Grounding large language models (LLMs) in domain-specific tasks like post-hoc dash-cam driving video analysis is challenging due to their general-purpose training and lack of structured inductive biases. As vision is often the sole modality available for such analysis (i.e. no LiDAR, GPS, etc.), existing video-basedvision-language models (V-VLMs) struggle with spatial reasoning, causal inference, and explainability of events in the input video. To this end, we introduce iFinder, a structured semantic grounding framework that decouples perception from reasoning by translating dash-cam videos into a hierarchical, interpretable data structure for LLMs. iFinder operates as a modular, training-free pipeline that employs pretrained vision models to extract critical cues—object pose, lane positions, and object trajectories—which are hierarchically organized into frame and video-level structures. Combined with a three-block prompting strategy, it enables step-wise, grounded reasoning for the LLM to refine a peer V-VLM’s outputs and provide accurate reasoning. Evaluations on four public dash-cam video benchmarks show that iFinder’s proposed grounding with domain-specific cues—especially object orientation and global context—significantly outperforms end-to-end V-VLMs on four zero-shot driving benchmarks, with up to 39% gains in accident reasoning accuracy. By grounding LLMs with driving domain-specific representations, iFinder offers a zero-shot, interpretable, and reliable alternativeto end-to-end V-VLMs for post-hoc driving video understanding

Read more

NeurIPS 2025 in San Diego from November 30th to December 5th, 2025

/in /by

NEC Laboratories America is heading to San Diego for NeurIPS 2025, where our researchers will present cutting-edge work spanning optimization, AI systems, language modeling, and trustworthy machine learning. multi-agent coordination, scalable training, efficient inference, and techniques for detecting LLM-generated text.

Read more

Mapillary Vistas Validation for Fine-Grained Traffic Signs: A Benchmark Revealing Vision-Language Model Limitations

/in /by

Obtaining high-quality fine-grained annotations for traffic signs is critical for accurate and safe decision-making in autonomous driving. Widely used datasets, such as Mapillary, often provide only coarse-grained labels without distinguishing semantically important types such as stop signs or speed limit signs. To this end, we present a new validation set for traffic signs derived from the Mapillary dataset called Mapillary Vistas Validation for Traffic Signs (MVV), where we decompose composite traffic signs into granular, semantically meaningful categories. The dataset includes pixel-level instance masks and has been manually annotated by expert annotators to ensure label fidelity. Further, we benchmark several state-of-the-art VLMs against the self-supervised DINOv2 model on this dataset and show that DINOv2 consistently outperforms all VLM baselines not only on traffic sign recognition, but also on heavily represented categories like vehicles and humans. Our analysis reveals significant limitations in current vision-language models for fine-grained visual understanding and establishes DINOv2 as a strong baseline for dense semantic matching in autonomous driving scenarios. This dataset and evaluation framework pave the way for more reliable, interpretable, and scalable perception systems. Code and data are available at: https://github.com/nec-labs-ma/relabeling

Read more

Abhishek Aich is Organizing the Anomaly Detection with Foundation Models Workshop, held in conjunction with ICCV 2025

/in /by

We are proud to share that our Abhishek Aich is serving as one of the organizers of the Anomaly Detection with Foundation Models Workshop, held in conjunction with the International Conference on Computer Vision, October 20, 2025, 08:55 AM – 12:15 PM HST in Room 314 at theHawaii Convention Center, Honolulu, HI.

Read more

Sparsh Garg Presents Mapillary Vistas Validation for Fine-Grained Traffic Signs at DataCV 2025

/in /by

Our Sparsh Garg, a Senior Associate Researcher in the Media Analytics Department, will present “Mapillary Vistas Validation for Fine-Grained Traffic Signs: A Benchmark Revealing Vision-Language Model Limitations” at the Data Computer Vision (DataCV) 2025 workshop as part of ICCV 2025 in Honolulu, Hawai’i, on Sunday, October 19th, from 11:15 am – 11:25 am.

Read more

iFinder: Structured Zero-Shot Vision-Based LLM Grounding for Dash-Cam Video Reasoning

/in /by

Grounding large language models (LLMs) in domain-specific tasks like post-hoc dash-cam driving video analysis is challenging due to their general-purpose training and lack of structured inductive biases. As vision is often the sole modality available for such analysis (i.e., no LiDAR, GPS, etc.), existing video-based vision-language models (V-VLMs) struggle with spatial reasoning, causal inference, and explainability of events in the input video. To this end, we introduce iFinder, a structured semantic grounding framework that decouples perception from reasoning by translating dash-cam videos into a hierarchical, interpretable data structure for LLMs. iFinder operates as a modular, training-free pipeline that employs pretrained vision models to extract critical cues — object pose, lane positions, and object trajectories — which are hierarchically organized into frame- and video-level structures. Combined with a three-block prompting strategy, it enables step-wise, grounded reasoning for the LLM to refine a peer V-VLM’s outputs and provide accurate reasoning. Evaluations on four public dash-cam video benchmarks show that iFinder’s proposed grounding with domain-specific cues, especially object orientation and global context, significantly outperforms end-to-end V-VLMs on four zero-shot driving benchmarks, with up to 39% gains in accident reasoning accuracy. By grounding LLMs with driving domain-specific representations, iFinder offers a zero-shot, interpretable, and reliable alternative to end-to-end V-VLMs for post-hoc driving video understanding.

Read more

Progressive Token Length Scaling in Transformer Encoders for Efficient Universal Segmentation

/in /by

A powerful architecture for universal segmentation relies on transformers that encode multi-scale image features and decode object queries into mask predictions. With efficiency being a high priority for scaling such models, we observed that the state-of-the-art method Mask2Former uses >50% of its compute only on the transformer encoder. This is due to the retention of a full-length token-level representation of all backbone feature scales at each encoder layer. With this observation, we propose a strategy termed PROgressive Token Length SCALing for Efficient transformer encoders (PRO-SCALE) that can be plugged-in to the Mask2Former segmentation architecture to significantly reduce the computational cost. The underlying principle of PRO-SCALE is: progressively scale the length of the tokens with the layers of the encoder. This allows PRO-SCALE to reduce computations by a large margin with minimal sacrifice in performance (?52% encoder and ? 27% overall GFLOPs reduction with no drop in performance on COCO dataset). Experiments conducted on public benchmarks demonstrates PRO-SCALE’s flexibility in architectural configurations, and exhibits potential for extension beyond the settings of segmentation tasks to encompass object detection. Code available here: https://github.com/abhishekaich27/proscale-pytorch

Read more

NEC Labs America Attends the 39th Annual AAAI Conference on Artificial Intelligence #AAAI25

/in /by

Our NEC Lab America team attended the Thirty-Ninth AAAI Conference on Artificial Intelligence (AAAI-25), in Philadelphia, Pennsylvania at the Pennsylvania Convention Center from February 25 to March 4, 2025. The purpose of the AAAI conference series was to promote research in AI and foster scientific exchange between researchers, practitioners, scientists, students, and engineers.

Read more

Improving the Efficiency-Accuracy Trade-off of DETR-Style Models in Practice

/in /by

This report aims to provide a comprehensive view on the inference efficiency of DETR-style detection models. We provide the effect of the basic efficiency techniques and identify the factors that are easily applicable yet effectively improve the efficiency-accuracy trade-off. Specifically, we explore the effect of input resolution, multi-scale feature enhancement, and backbone pre-training. Our experiments support that 1) improving the detection accuracy for smaller objects while minimizing the increase in inference cost is a good strategy to achieve a better trade-off between accuracy and efficiency. 2) Multi-scale feature enhancement can be lightened with marginal accuracy loss and 3) improved backbone pre-training can further enhance the trade-off.

Read more