FLEX-LBP：用反向传播学习局部二值模式参数，纹理分类更准
FLEX-LBP: Learning Local Binary Patterns with Exact Binary Inference for Texture Classification
手工调 LBP 参数这事儿终于可以交给梯度了。FLEX-LBP 只学 90 个参数，推理开销不变，精度却超过 ResNet-50 特征和一堆经典 LBP 变体，做工业检测或医学图像分析的朋友可以直接拿 PyTorch 层来用。
FLEX-LBP 是一个新方法，把经典纹理描述子 Local Binary Patterns（LBP）中原本靠手工固定的半径、采样角度、颜色变换和阈值改为通过反向传播自动学习，仅有 90 个可学习参数。前向传播仍计算精确的二进制编码和硬直方图计数，只靠 straight-through 估计器在反向传播中传递梯度，因此部署时的推理成本与固定 LBP 完全一致，且描述子保持可解释的硬二值形式。
在六个彩色纹理基准上的消融实验显示，最值得学习的部分随数据集而变；一套统一配置在冻结颜色变换、只学习几何和阈值的情况下，把同一固定描述子的最近邻分类精度平均提升 3.55 个百分点（五次随机种子），在六个基准中五个显著提升、无一下降。配合线性判别读出再提升 0.9 个点，完全学习版本提升 2.7 个点且均值最高。它在六个基准中的五个上超过五个经典 LBP 系列描述子、PCANet 和神经 LBP，均值最近邻精度超过参数量 2350 万的冻结 ImageNet ResNet-50 特征。在 Kather 结直肠癌组织学基准上，完全学习版本达到 93.8%，显著高于最佳经典描述子 Completed LBP 的 92.8%。作者还发现噪声会淹没单像素比较、光源变化会翻转通道间比较，采用中值采样或灰世界归一化可恢复 96-97% 的精度。
FLEX-LBP: Learning Local Binary Patterns with Exact Binary Inference for Texture Classification
Local Binary Patterns (LBP) remain among the most widely used texture descriptors, from industrial inspection to medical imaging. Yet their radius, sampling angles, color transform and thresholds are fixed by hand for each dataset. We present FLEX-LBP, which learns these parameters by backpropagation while every forward pass computes exact binary codes and hard histogram counts. A straight-through estimator acts only in the backward pass, so the deployed descriptor is an interpretable hard-binary LBP with 90 learnable parameters and unchanged inference cost. In a controlled ablation on six color texture benchmarks, the component worth learning is dataset-dependent. One configuration, applied unchanged everywhere, learns the geometry and thresholds with the color transform frozen. It improves the nearest-neighbor accuracy of the identical fixed descriptor by 3.55 points on average over five seeds, significantly on five of six benchmarks and never significantly worse. With a linear discriminant readout, it gains 0.9 points; the fully learned descriptor gains 2.7 and has the highest mean. FLEX-LBP is more accurate than five classical LBP-family descriptors, PCANet and a neural LBP on five of six benchmarks. Its mean nearest-neighbor accuracy exceeds that of frozen ImageNet ResNet-50 features (23.5 million parameters). On the Kather colorectal cancer histology benchmark, the fully learned descriptor reaches 93.8%, significantly above the best classical descriptor (Completed LBP, 92.8%). The learned radii adapt in directions that recur across seeds. Noise drowns single-pixel comparisons and illuminant change flips inter-channel ones; median sampling or gray-world normalization restores 96-97%. The code is available as a drop-in PyTorch layer at https://github.com/medalimoussa/FLEX-LBP.
本条情报归属 AITOP「论文」核心追踪栏目。在跨区域产业观察坐标中，该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线，反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括：FLEX-LBP、LBP、纹理分类、PyTorch，读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。
信源核验说明：本文原始线索采编自「arXiv cs.LG」（@Mohamed Alimoussa, Amal El Kaid），经 AITOP 多维评分管线结构化提炼。