6 citations · 9 across the 13 of their papers we have counts for
14 papers
CXR-Retrieve: Compositional Text-to-Image Retrieval in Chest Radiography
Tomer Erez, Moshe Kimhi, Chaim Baskin +1
Large chest radiography archives are difficult to search because most studies are paired only with free-text reports rather than structured clinical annotations. Vision-language mo…
Look Where It Matters: High-Resolution Crops Retrieval for Efficient VLMs
Nimrod Shabtay, Moshe Kimhi, Artem Spector +5
Vision-language models (VLMs) typically process images at a native high-resolution, forcing a trade-off between accuracy and computational efficiency: high-resolution inputs captur…
CARES: Context-Aware Resolution Selector for VLMs
Moshe Kimhi, Nimrod Shabtay, Raja Giryes +2
Large vision-language models (VLMs) commonly process images at native or high resolution to remain effective across tasks. This inflates visual tokens ofter to 97-99% of total toke…
WAVECLIP: Wavelet Tokenization for Adaptive-Resolution CLIP
Moshe Kimhi, Erez Koifman, Ehud Rivlin +2
We introduce WAVECLIP, a single unified model for adaptive resolution inference in CLIP, enabled by wavelet-based tokenization. WAVECLIP replaces standard patch embeddings with a m…
: Reconstruction, Raw, and Rain: Deraining Directly in the Bayer Domain
Nate Rothschild, Moshe Kimhi, Avi Mendelson +1
Image reconstruction from corrupted images is crucial across many domains. Most reconstruction networks are trained on post-ISP sRGB images, even though the image-signal-processing…
Benchmarking Adversarial Patch Selection and Location
Shai Kimhi, Avi Mendlson, Moshe Kimhi
Adversarial patch attacks threaten the reliability of modern vision models. We present PatchMap, the first spatially exhaustive benchmark of patch placement, built by evaluating ov…
Maximal Brain Damage Without Data or Optimization: Disrupting Neural Networks via Sign-Bit Flips
Ido Galil, Moshe Kimhi, Ran El-Yaniv
Deep Neural Networks (DNNs) can be catastrophically disrupted by flipping only a handful of parameter bits. We introduce Deep Neural Lesion (DNL), a data-free and optimizationfree…
Hysteresis Activation Function for Efficient Inference
Moshe Kimhi, Idan Kashani, Avi Mendelson +1
The widely used ReLU is favored for its hardware efficiency, {as the implementation at inference is a one bit sign case,} yet suffers from issues such as the ``dying ReLU'' problem…
Context-aware Prompt Tuning: Advancing In-Context Learning with Adversarial Methods
Tsachi Blau, Moshe Kimhi, Yonatan Belinkov +2
Fine-tuning Large Language Models (LLMs) typically involves updating at least a few billions of parameters. A more parameter-efficient approach is Prompt Tuning (PT), which updates…
Robot Instance Segmentation with Few Annotations for Grasping
Moshe Kimhi, David Vainshtein, Chaim Baskin +1
The ability of robots to manipulate objects relies heavily on their aptitude for visual perception. In domains characterized by cluttered scenes and high object variability, most m…
Noisy Annotations in Semantic Segmentation
Moshe Kimhi, Omer Kerem, Eden Grad +2
Obtaining accurate labels for instance segmentation is particularly challenging due to the complex nature of the task. Each image necessitates multiple annotations, encompassing no…
Semi-Supervised Semantic Segmentation via Marginal Contextual Information
Moshe Kimhi, Shai Kimhi, Evgenii Zheltonozhskii +2
We present a novel confidence refinement scheme that enhances pseudo labels in semi-supervised semantic segmentation. Unlike existing methods, which filter pixels with low-confiden…
AMED: Automatic Mixed-Precision Quantization for Edge Devices
Moshe Kimhi, Tal Rozen, Avi Mendelson +1
Quantized neural networks are well known for reducing the latency, power consumption, and model size without significant harm to the performance. This makes them highly appropriate…
Bimodal Distributed Binarized Neural Networks
Tal Rozen, Moshe Kimhi, Brian Chmiel +2
Binary Neural Networks (BNNs) are an extremely promising method to reduce deep neural networks' complexity and power consumption massively. Binarization techniques, however, suffer…