Search Results - "Chavan, Arnav"

Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space by Chavan, Arnav, Shen, Zhiqiang, Liu, Zhuang, Liu, Zechun, Cheng, Kwang-Ting, Xing, Eric

“…This paper explores the feasibility of finding an optimal sub-model from a vision transformer and introduces a pure vision transformer slimming (ViT-Slim)…”
Get full text

Deep learning for detection and segmentation of artefact and disease instances in gastrointestinal endoscopy by Ali, Sharib, Dmitrieva, Mariia, Ghatwary, Noha, Bano, Sophia, Polat, Gorkem, Temizel, Alptekin, Krenzer, Adrian, Hekalo, Amar, Guo, Yun Bo, Matuszewski, Bogdan, Gridach, Mourad, Voiculescu, Irina, Yoganand, Vishnusai, Chavan, Arnav, Raj, Aryan, Nguyen, Nhan T., Tran, Dat Q., Huynh, Le Duy, Boutry, Nicolas, Rezvy, Shahadate, Chen, Haijian, Choi, Yoon Ho, Subramanian, Anand, Balasubramanian, Velmurugan, Gao, Xiaohong W., Hu, Hongyu, Liao, Yusheng, Stoyanov, Danail, Daul, Christian, Realdon, Stefano, Cannizzaro, Renato, Lamarque, Dominique, Tran-Nguyen, Terry, Bailey, Adam, Braden, Barbara, East, James E., Rittscher, Jens

“…•EndoCV2020, an endoscopy computer vision challenge addresses eminent problems in endoscopy.•Deep learning methods built to address artefacts and disease…”
Get full text

Rescaling CNN Through Learnable Repetition of Network Parameters by Chavan, Arnav, Bamba, Udbhav, Tiwari, Rishabh, Gupta, Deepak

“…Deeper and wider CNNs are known to provide improved performance for deep learning tasks. However, most such networks have poor performance gain per parameter…”
Get full text

Dynamic Kernel Selection for Improved Generalization and Memory Efficiency in Meta-learning by Chavan, Arnav, Tiwari, Rishabh, Bamba, Udbhav, Gupta, Deepak K.

“…Gradient based meta-learning methods are prone to overfit on the meta-training set, and this behaviour is more prominent with large and complex networks…”
Get full text

On Designing Light-Weight Object Trackers Through Network Pruning: Use CNNS or Transformers? by Aggarwal, Saksham, Gupta, Taneesh, Sahu, Pawan K., Chavan, Arnav, Tiwari, Rishabh, Prasad, Dilip K., Gupta, Deepak K.

“…Object trackers deployed on low-power devices need to be light-weight, however, most of the current state-of-the-art (SOTA) methods rely on using compute-heavy…”
Get full text

Surgical Feature-Space Decomposition of LLMs: Why, When and How? by Chavan, Arnav, Lele, Nahush, Gupta, Deepak

“…Low-rank approximations, of the weight and feature space can enhance the performance of deep learning models, whether in terms of improving generalization or…”
Get full text

Rethinking Compression: Reduced Order Modelling of Latent Features in Large Language Models by Chavan, Arnav, Lele, Nahush, Gupta, Deepak

“…Due to the substantial scale of Large Language Models (LLMs), the direct application of conventional compression methodologies proves impractical. The…”
Get full text

Beyond Uniform Scaling: Exploring Depth Heterogeneity in Neural Architectures by T, Akash Guna R, Chavan, Arnav, Gupta, Deepak

“…Conventional scaling of neural networks typically involves designing a base network and growing different dimensions like width, depth, etc. of the same by…”
Get full text

Faster and Lighter LLMs: A Survey on Current Challenges and Way Forward by Chavan, Arnav, Magazine, Raghav, Kushwaha, Shubham, Debbah, Mérouane, Gupta, Deepak

“…Despite the impressive performance of LLMs, their widespread adoption faces challenges due to substantial computational and memory requirements during…”
Get full text

One-for-All: Generalized LoRA for Parameter-Efficient Fine-tuning by Chavan, Arnav, Liu, Zhuang, Gupta, Deepak, Xing, Eric, Shen, Zhiqiang

“…We present Generalized LoRA (GLoRA), an advanced approach for universal parameter-efficient fine-tuning tasks. Enhancing Low-Rank Adaptation (LoRA), GLoRA…”
Get full text

Patch Gradient Descent: Training Neural Networks on Very Large Images by Gupta, Deepak K, Mago, Gowreesh, Chavan, Arnav, Prasad, Dilip K

“…Traditional CNN models are trained and tested on relatively low resolution images (<300 px), and cannot be directly operated on large-scale images due to…”
Get full text

Transfer Learning Gaussian Anomaly Detection by Fine-tuning Representations by Rippel, Oliver, Chavan, Arnav, Lei, Chucai, Merhof, Dorit

“…Current state-of-the-art anomaly detection (AD) methods exploit the powerful representations yielded by large-scale ImageNet training. However, catastrophic…”
Get full text

Dynamic Kernel Selection for Improved Generalization and Memory Efficiency in Meta-learning by Chavan, Arnav, Tiwari, Rishabh, Bamba, Udbhav, Gupta, Deepak K

“…Gradient based meta-learning methods are prone to overfit on the meta-training set, and this behaviour is more prominent with large and complex networks…”
Get full text

ChipNet: Budget-Aware Pruning with Heaviside Continuous Approximations by Tiwari, Rishabh, Bamba, Udbhav, Chavan, Arnav, Gupta, Deepak K

“…Structured pruning methods are among the effective strategies for extracting small resource-efficient convolutional neural networks from their dense…”
Get full text

Rescaling CNN through Learnable Repetition of Network Parameters by Chavan, Arnav, Bamba, Udbhav, Tiwari, Rishabh, Gupta, Deepak

“…Deeper and wider CNNs are known to provide improved performance for deep learning tasks. However, most such networks have poor performance gain per parameter…”
Get full text

On Designing Light-Weight Object Trackers through Network Pruning: Use CNNs or Transformers? by Aggarwal, Saksham, Gupta, Taneesh, Sahu, Pawan Kumar, Chavan, Arnav, Tiwari, Rishabh, Prasad, Dilip K, Gupta, Deepak K

“…Object trackers deployed on low-power devices need to be light-weight, however, most of the current state-of-the-art (SOTA) methods rely on using compute-heavy…”
Get full text

Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space by Chavan, Arnav, Shen, Zhiqiang, Liu, Zhuang, Liu, Zechun, Cheng, Kwang-Ting, Xing, Eric

“…This paper explores the feasibility of finding an optimal sub-model from a vision transformer and introduces a pure vision transformer slimming (ViT-Slim)…”
Get full text

Multi-Plateau Ensemble for Endoscopic Artefact Segmentation and Detection by Jadhav, Suyog, Bamba, Udbhav, Chavan, Arnav, Tiwari, Rishabh, Raj, Aryan

“…http://ceur-ws.org/Vol-2595/endoCV2020_paper_id_20.pdf Endoscopic artefact detection challenge consists of 1) Artefact detection, 2) Semantic segmentation, and…”
Get full text

RCV2023 Challenges: Benchmarking Model Training and Inference for Resource-Constrained Deep Learning by Tiwari, Rishabh, Chavan, Arnav, Gupta, Deepak, Mago, Gowreesh, Gupta, Animesh, Gupta, Akash, Sharan, Suraj, Yang, Yukun, Zhao, Shanwei, Wang, Shihao, Kwak, Youngjun, Jeong, Seonghun, Lee, Yunseung, Kim, Changick, Kim, Subin, Gankhuyag, Ganzorig, Jung, Ho, Ryu, Junwhan, Kim, HaeMoon, Kim, Byeong H., Vo, Tu, Zaheer, Sheir, Holston, Alexander, Park, Chan, Dixit, Dheemant, Lele, Nahush, Bhushan, Kushagra, Bhowmick, Debjani, Arya, Devanshu, Gulshad, Sadaf, Habibian, Amirhossein, Ghodrati, Amir, Bejnordi, Babak, Gupta, Jai, Liu, Zhuang, Yu, Jiahui, Prasad, Dilip, Shen, Zhiqiang

“…This paper delves into the results of two resource-constrained deep learning challenges, part of the workshop on Resource-Efficient Deep Learning for Computer…”
Get full text

Deep learning for detection and segmentation of artefact and disease instances in gastrointestinal endoscopy by Ali, Sharib, Dmitrieva, Mariia, Ghatwary, Noha, Bano, Sophia, Polat, Gorkem, Temizel, Alptekin, Krenzer, Adrian, Hekalo, Amar, Guo, Yun Bo, Matuszewski, Bogdan, Gridach, Mourad, Voiculescu, Irina, Yoganand, Vishnusai, Chavan, Arnav, Raj, Aryan, Nguyen, Nhan T, Tran, Dat Q, Huynh, Le Duy, Boutry, Nicolas, Rezvy, Shahadate, Chen, Haijian, Choi, Yoon Ho, Subramanian, Anand, Balasubramanian, Velmurugan, Gao, Xiaohong W, Hu, Hongyu, Liao, Yusheng, Stoyanov, Danail, Daul, Christian, Realdon, Stefano, Cannizzaro, Renato, Lamarque, Dominique, Tran-Nguyen, Terry, Bailey, Adam, Braden, Barbara, East, James, Rittscher, Jens

“…The Endoscopy Computer Vision Challenge (EndoCV) is a crowd-sourcing initiative to address eminent problems in developing reliable computer aided detection and…”
Get full text