activity
20192026
most citedPosition, Padding and Predictions: A Deeper Look at Position Information in CNNs

42 citations · 62 across the 11 of their papers we have counts for

collaborators
Showing cs.CVShow all

11 papers · 1 filter

cs.CV2026

What, Where, and How: Probing Spatiotemporal Representations in Video Foundation Models

Sharon S. Musa, Fereshteh Forghani, Harrish Thasarathan +3

Self-supervised video foundation models learn rich spatiotemporal representations, yet it remains unclear what visual concepts these representations encode, where they emerge acros…

cs.CV2026

Structuring Sparsity: Block-Sparse Featurizers Capture Visual Concept Manifolds

Thomas Fel, Matthew Kowal, Mozes Jacobs +22

What is the geometry of a visual percept? The most widely used protocols for decomposing neural network representations into interpretable parts treat concepts as isolated directio…

cs.CV2024

Visual Concept Connectome (VCC): Open World Concept Discovery and their Interlayer Connections in Deep Models

Matthew Kowal, Richard P. Wildes, Konstantinos G. Derpanis

Understanding what deep network models capture in their learned representations is a fundamental challenge in computer vision. We present a new methodology to understanding such vi…

cs.CV20241 cited

Understanding Video Transformers via Universal Concept Discovery

Matthew Kowal, Achal Dave, Rares Ambrus +3

This paper studies the problem of concept-based interpretability of transformer representations for videos. Concretely, we seek to explain the decision-making process of video tran…

cs.CV2021

Simpler Does It: Generating Semantic Labels with Objectness Guidance

Md Amirul Islam, Matthew Kowal, Sen Jia +2

Existing weakly or semi-supervised semantic segmentation methods utilize image or box-level supervision to generate pseudo-labels for weakly labeled images. However, due to the lac…

cs.CV2021

SegMix: Co-occurrence Driven Mixup for Semantic Segmentation and Adversarial Robustness

Md Amirul Islam, Matthew Kowal, Konstantinos G. Derpanis +1

In this paper, we present a strategy for training convolutional neural networks to effectively resolve interference arising from competing hypotheses relating to inter-categorical…