activity
20212024
most citedMViTv2: Improved Multiscale Vision Transformers for Classification and Detection

29 citations · 59 across the 7 of their papers we have counts for

collaborators

7 papers

cs.CV2024

Do Vision and Language Encoders Represent the World Similarly?

Mayug Maniparambil, Raiymbek Akshulakov, Yasser Abdelaziz Dahou Djilali +4

Aligned text-image encoders such as CLIP have become the de facto model for vision-language tasks. Furthermore, modality-specific encoders achieve impressive performances in their…

cs.CV20241 cited

DrNet: Dynamic Reversible Dual-Residual Networks for Memory-Efficient Finetuning

Chen Zhao, Shuming Liu, Karttikeya Mangalam +5

Large pretrained models are increasingly crucial in modern computer vision tasks. These models are typically used in downstream tasks by end-to-end finetuning, which is highly memo…

cs.CV202319 cited

EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding

Karttikeya Mangalam, Raiymbek Akshulakov, Jitendra Malik

We introduce EgoSchema, a very long-form video question-answering dataset, and benchmark to evaluate long video understanding capabilities of modern vision and language systems. De…

cs.CV20232 cited

Diffusion Models as Masked Autoencoders

Chen Wei, Karttikeya Mangalam, Po-Yao Huang +7

There has been a longstanding belief that generation can facilitate a true understanding of visual data. In line with this, we revisit generatively pre-training visual representati…

cs.CV2023

Reversible Vision Transformers

Karttikeya Mangalam, Haoqi Fan, Yanghao Li +4

We present Reversible Vision Transformers, a memory efficient architecture design for visual recognition. By decoupling the GPU memory requirement from the depth of the model, Reve…

cs.CV20218 cited

Overcoming Mode Collapse with Adaptive Multi Adversarial Training

Karttikeya Mangalam, Rohin Garg

Generative Adversarial Networks (GANs) are a class of generative models used for various applications, but they have been known to suffer from the mode collapse problem, in which s…