|
- Evaluating the Robustness of Neural Networks: An Extreme Value. . .
Experimental results on various networks, including ResNet, Inception-v3 and MobileNet, show that (i) CLEVER is aligned with the robustness indication measured by the $\ell_2$ and $\ell_\infty$ norms of adversarial examples from powerful attacks, and (ii) defended networks using defensive distillation or bounded ReLU indeed give better CLEVER
- Counterfactual Debiasing for Fact Verification - OpenReview
016 namely CLEVER, which is augmentation-free 017 and mitigates biases on the inference stage 018 Specifically, we train a claim-evidence fusion 019 model and a claim-only model independently 020 Then, we obtain the final prediction via sub-021 tracting output of the claim-only model from 022 output of the claim-evidence fusion model,
- Leaving the barn door open for Clever Hans: Simple features predict. . .
This phenomenon, widely known in human and animal experiments, is often referred to as the ‘Clever Hans’ effect, where tasks are solved using spurious cues, often involving much simpler processes than those putatively assessed Previous research suggests that language models can exhibit this behaviour as well
- On the Planning Abilities of Large Language Models : A Critical . . .
their Clever Hans effect [1] with the actual planning being done by the humans in the loop rather than the LLMs themselves We thus separate our evaluation into two modes–autonomous and as assistants to external planners reasoners There have also been efforts which mostly depended on
- Learnable Representative Coefficient Image Denoiser for. . .
Recently, HSI denoising models based on representative coefficient images (RCIs) under the spectral low-rank decomposition framework have garnered significant attention due to their clever utilization of spatial-spectral information in HSI at a low cost
- TRANSFORMERS CAN NAVIGATE MAZES WITH MULTI-STEP PREDICTION - OpenReview
the work identifies a Clever-Hans cheat based on shortcuts in teacher forced training similar to theo-retical shortcomings identified in Wang et al (2024b) This demonstrates that while transformers can represent world states for mazes, they may struggle in planning that requires significant foresight A
- From Control Application to Control Logic: PLC Decompile Framework. . .
Then, to normalize the control application decompile process, an intermediate representation (IR) is designed, which can simplify the analysis process and enhance the extensibility of CLEVER Finally, a heuristic data flow analysis algorithm is proposed to find variable dependency, and a sequential parsing method is utilized to reconstruct the
- LENFusion: A Joint Low-Light Enhancement and Fusion Network for. . .
The enhancement is performed in two stages In the initial stage, LAN applies adaptive luminance adjustment to the original visible image Subsequently, RFN achieves secondary enhancement and feature fusion with a clever combination of dual-attention mechanism, which motivates the fusion results to have high contrast and sharpness
|
|
|