9 citations · 22 across the 12 of their papers we have counts for
13 papers
SCRAMBLe : Enhancing Multimodal LLM Compositionality with Synthetic Preference Data
Samarth Mishra, Kate Saenko, Venkatesh Saligrama
Compositionality, or correctly recognizing scenes as compositions of atomic visual concepts, remains difficult for multimodal large language models (MLLMs). Even state of the art M…
SPARC: Score Prompting and Adaptive Fusion for Zero-Shot Multi-Label Recognition in Vision-Language Models
Kevin Miller, Samarth Mishra, Aditya Gangrade +2
Zero-shot multi-label recognition (MLR) with Vision-Language Models (VLMs) faces significant challenges without training data, model tuning, or architectural modifications. Existin…
SynCDR : Training Cross Domain Retrieval Models with Synthetic Data
Samarth Mishra, Carlos D. Castillo, Hongcheng Wang +2
In cross-domain retrieval, a model is required to identify images from the same semantic category across two visual domains. For instance, given a sketch of an object, a model need…
Learning Human Action Recognition Representations Without Real Humans
Howard Zhong, Samarth Mishra, Donghyun Kim +7
Pre-training on massive video datasets has become essential to achieve high action recognition performance on smaller downstream datasets. However, most large-scale video datasets…
VisDA 2022 Challenge: Domain Adaptation for Industrial Waste Sorting
Dina Bashkirova, Samarth Mishra, Diala Lteif +16
Label-efficient and reliable semantic segmentation is essential for many real-life applications, especially for industrial settings with high visual diversity, such as waste sortin…
Fine-grained Few-shot Recognition by Deep Object Parsing
Ruizhao Zhu, Pengkai Zhu, Samarth Mishra +1
We propose a new method for fine-grained few-shot recognition via deep object parsing. In our framework, an object is made up of K distinct parts and for each part, we learn a dict…
Learning Compositional Representations for Effective Low-Shot Generalization
Samarth Mishra, Pengkai Zhu, Venkatesh Saligrama
We propose Recognition as Part Composition (RPC), an image encoding approach inspired by human cognition. It is based on the cognitive theory that humans recognize complex objects…
Task2Sim : Towards Effective Pre-training and Transfer from Synthetic Data
Samarth Mishra, Rameswar Panda, Cheng Perng Phoo +5
Pre-training models on Imagenet or other massive datasets of real images has led to major advances in computer vision, albeit accompanied with shortcomings related to curation cost…
VisDA-2021 Competition Universal Domain Adaptation to Improve Performance on Out-of-Distribution Data
Dina Bashkirova, Dan Hendrycks, Donghyun Kim +5
Progress in machine learning is typically measured by training and testing a model on the same distribution of data, i.e., the same domain. This over-estimates future accuracy on o…
Effectively Leveraging Attributes for Visual Similarity
Samarth Mishra, Zhongping Zhang, Yuan Shen +3
Measuring similarity between two images often requires performing complex reasoning along different axes (e.g., color, texture, or shape). Insights into what might be important for…
Surprisingly Simple Semi-Supervised Domain Adaptation with Pretraining and Consistency
Samarth Mishra, Kate Saenko, Venkatesh Saligrama
Most modern unsupervised domain adaptation (UDA) approaches are rooted in domain alignment, i.e., learning to align source and target features to learn a target domain classifier u…
Self-supervised Visual Attribute Learning for Fashion Compatibility
Donghyun Kim, Kuniaki Saito, Samarth Mishra +3
Many self-supervised learning (SSL) methods have been successful in learning semantically meaningful visual representations by solving pretext tasks. However, prior work in SSL foc…
Faster Algorithms for Weighted Recursive State Machines
Krishnendu Chatterjee, Bernhard Kragl, Samarth Mishra +1
Pushdown systems (PDSs) and recursive state machines (RSMs), which are linearly equivalent, are standard models for interprocedural analysis. Yet RSMs are more convenient as they (…