ChengYue's Cat

在弱监督语义分割任务中,通过分类任务可以得到CAM结果,为了进一步更加准确的得到伪分割标签,往往会使用DenseCRF方法来refine得到的CAM结果。 该方法的实现如下所示,其中包括了一个超参数 $\alpha$, 该参数越大,则像素被分类成背景区域的可能性越小,反之越大。

def _crf_with_alpha(cam_dict, name, alpha=10):
    # cam_dict 是一个存放了各个类别对应的像素mask的字典,图像有多少个 gt_label 字典里就存了多少个类的 mask
    orig_img = np.ascontiguousarray(np.uint8(Image.open(os.path.join('/data/data/Seg_Data/PASCAL-VOC/VOCdevkit/VOC2012/JPEGImages', name + '.jpg'))))
    v = np.array(list(cam_dict.values()))                               # n_cls x h x w 
    # 计算背景得分, alpha值越大,背景得分越低,这意味着有更多的像素会被分为前景
    bg_score = np.power(1 - np.max(v, axis=0, keepdims=True), alpha)    # 1 x h x w
    bgcam_score = np.concatenate((bg_score, v), axis=0)                 # (n_cls + 1) x h x w, concat the background 
    
    # densecrf inference
    crf_score = crf_inference(orig_img, bgcam_score, labels=bgcam_score.shape[0])   

    # save desnecrf results
    n_crf_al = dict()
    # background score
    n_crf_al[0] = crf_score[0]                                          
    for i, key in enumerate(cam_dict.keys()):
        n_crf_al[key + 1] = crf_score[i + 1]

    return n_crf_al

def crf_inference(img, probs, t=10, scale_factor=1, labels=21):
    import pydensecrf.densecrf as dcrf
    from pydensecrf.utils import unary_from_softmax

    h, w = img.shape[:2]
    n_labels = labels

    d = dcrf.DenseCRF2D(w, h, n_labels)
    unary = unary_from_softmax(probs)
    unary = np.ascontiguousarray(unary)
    d.setUnaryEnergy(unary)
    d.addPairwiseGaussian(sxy=3/scale_factor, compat=3)
    d.addPairwiseBilateral(sxy=80/scale_factor, srgb=13, rgbim=np.copy(img), compat=10)
    Q = d.inference(t)

    return np.array(Q).reshape((n_labels, h, w))